Research map / Detection and segmentation / 3D detection and driving
DeepInteraction++: Multi-Modality Interaction for Autonomous Driving
Zeyu Yang, Nan Song, Wei Li, Xiatian Zhu, Li Zhang, Philip H. S. Torr
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add image-to-LiDAR representational interaction with L2I (bilateral instead of unilateral) (ablation) | DeepInteraction · nuScenes val | mAP: 69.2 -> 69.9 with image in decoder; 68.9 -> 69.4 | Improved |
| add image representation in decoder (MMPI on both modalities) (ablation) | DeepInteraction · nuScenes val | mAP/NDS: 69.2 -> 69.9 mAP, 72.2 -> 72.6 NDS | Improved |
| add multi-modal representational interaction encoder (ablation) | DeepInteraction++ · nuScenes val | mAP: 67.7 -> 70.6 | Improved |
| add LiDAR-guided polar attention (ablation) | DeepInteraction++ · nuScenes val | mAP/NDS: 70.32 -> 70.63 mAP, 73.02 -> 73.27 NDS | Improved |
| add LiDAR-guided polar attention (ablation) | DeepInteraction++ · Waymo (1/5 train) | L2 mAP: 66.95 -> 67.02 | No clear effect |
| keep image features in perspective form instead of BEV (ablation) | DeepInteraction++ · nuScenes val | mAP: 69.4 -> 70.3 | Improved |
| replace DETR decoder layers with MMPI for both modalities (ablation) | DeepInteraction++ · nuScenes val | mAP: 69.7 -> 70.6 | Improved |
| use alternating LiDAR and image interaction in decoder (ablation) | DeepInteraction++ · nuScenes val | NDS: 72.8 -> 73.3 | Improved |
| add multimodal interaction to the LiDAR-only baseline (pillar backbone) | DeepInteraction++ · nuScenes val (pillar) | mAP: 54.5 -> 65.6 | Improved |
| vary number of queries at train/inference (200/300/400) (ablation) | DeepInteraction · nuScenes val | mAP: 69.7 to 70.1 | No clear effect |
| swap DeepInteraction for DeepInteraction++ with R50 backbone | DeepInteraction · nuScenes val | NDS: 72.6 -> 72.9 | Improved |
| upgrade DeepInteraction to DeepInteraction++ for end-to-end planning | DeepInteraction · nuScenes val planning | avg collision rate (%): 0.25 -> 0.19 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 on most shared results.
- TransFusion — TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection With Transformers (CVPR 2022) · better on 4 of 5 shared results
- UniTR — UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation (ICCV 2023) · better on 1 of 2 shared results
- MSMDFusion — MSMDFusion: Fusing LiDAR and Camera at Multiple Scales With Multi-Depth Seeds for 3D Object Detection (CVPR 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Layer-Wise Modality Decomposition for Interpretable Multimodal Sensor Fusion (NeurIPS 2025 · similarity 0.87)
- M3Net: Multimodal Multi-task Learning for 3D Detection, Segmentation, and Occupancy Prediction in Autonomous Driving (AAAI 2025 · similarity 0.87)
- DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving (ICLR 2025 · similarity 0.86)
- DualAD: Disentangling the Dynamic and Static World for End-to-End Driving (CVPR 2024 · similarity 0.86)
- Generating Multimodal Driving Scenes via Next-Scene Prediction (CVPR 2025 · similarity 0.86)
- World Knowledge-Enhanced Reasoning Using Instruction-Guided Interactor in Autonomous Driving (AAAI 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
